Thank you for sharing.

I also tried vibe coding with Qwen3.8 (just give it a few lines of what you want, and step away). and you’re right, it does… something, but not at all how you want it. (obvious in hindsight)

Your Step 4 is how I use AI now. I use Deepseek Harness. I don’t use a dedicated plan mode, but I do tell it ‘let’s plan and write a TODO .md for a <task>’, and we discuss ways of implementing something, what libraries we can use, pit-falls, future-proofing etc., and it will write whatever we decide on in a TODO file. Only after each step has been discussed, I tell it to review the TODO and ask me if it has any more questions. Once it’s satisfied, I verify what it wrote in the TODO one last time, and when I’m satisfied I tell it to implement the TODO we just planned.

TODOs work quite well if you make and review them with the model before it implements it.

Not scientific, but I sometimes get Gemma4 check Qwen 3.8’s work because I noticed when a model knows its not their work, they’re a lot more critical. Might be helpful to get another model to review tests.

I’ve used pi.dev’s default compaction (this was a few months ago, it may have improved) and it lobotomized the model, so I kept if off, and made my model do a handoff for the next session. However, Deepseek harness’s compaction is very good. Unfortunately, if you use under 264K context, you have to modify its settings because its point of compaction is TOTAL - max_tokens - 16k reserve, and max_tokens is 64k. I had to modify the settings down to 16K (using Qwen 3.8, because there’s a bug in how DSH reads settings and it wasn’t working when I did it), and I still compact at 73% (88K) on 120K context (ie: 120 - 16k - 16K). But it’s really good. I’ve gone to 2M output tokens (100M cached) until I thought it was getting too dumb for the task and started a new session.

So yes, compaction can work well. Make sure your prefill speed is 1000tk/s+ or else it will be painful.

Look at rolling releases. I’ve used Mint but at the time (maybe still today) some projects required the latest ROCm drivers, and Mint’s repositories are just too slow to keep up with pace of AI. I decided to go with EndeavourOS since it’s a fork of Arch so it’s a rolling release, and you can keep up with the latest experimental AI hacks that are developed. The downside to a rolling release is that sometimes you update your computer and something stops working, like your sound drivers or Steam. But someone always finds a fix a few hours later. It doesn’t happen every time. I generally update my system when I need to, so about every month or two. I use EndeavourOS as my daily driver actually, so it’s not unstable at all. Anyway, look at rolling releases that have more than 1 maintainer. Look at their forum, see how helpful it is, etc.